CN114400062B

CN114400062B - Interpretation method and device of inspection report, computer equipment and storage medium

Info

Publication number: CN114400062B
Application number: CN202111577521.XA
Authority: CN
Inventors: 陶然; 陈思彤; 黄怡荣; 伍阳娥; 陈帆; 伍淑文; 刘怀学
Original assignee: Guangzhou Kingmed Diagnostics Central Co Ltd
Current assignee: Guangzhou Kingmed Diagnostics Central Co Ltd
Priority date: 2021-12-21
Filing date: 2021-12-21
Publication date: 2024-03-22
Anticipated expiration: 2041-12-21
Also published as: CN114400062A

Abstract

The embodiment of the invention discloses an interpretation method and device of a test report, computer equipment and a storage medium, wherein the method comprises the following steps: receiving an interpretation request sent by a client, wherein the interpretation request comprises inspection report information of a target inspection report; determining a display mode of a test result of the target test report by using the test report information; determining a target interpretation mode corresponding to the target inspection report according to the display mode and the interpretation mode corresponding to the display mode; and determining the interpretation result of the target inspection report based on the inspection report information and the target interpretation mode. When an interpretation request is received, the display mode of the inspection result of the target inspection report is obtained by utilizing the inspection report information, the target inspection report is interpreted by adopting the interpretation mode corresponding to the display mode, and the interpretation result is obtained, so that the method not only can be suitable for the interpretation of the inspection reports of different display modes, but also can realize the real-time interpretation of the target inspection report.

Description

Interpretation method and device of inspection report, computer equipment and storage medium

Technical Field

The present invention relates to the field of intelligent medical technology, and in particular, to a method and apparatus for interpreting test results, a computer device, and a storage medium.

Background

In medical testing, in addition to professional test results being made, a user may want to understand the meaning behind those professional test results to get an interpretation of the test report for the patient's test report.

In the prior art, different test reports have different conclusions, so that a way for effectively reading various types of test reports is still lacking for reading the test reports.

Disclosure of Invention

The invention mainly aims to provide a method, a device, a computer device and a storage medium for interpreting test reports, which can solve the problem that a report interpretation mode capable of providing effective interpretation is lacking in the prior art.

To achieve the above object, a first aspect of the present invention provides a method for interpreting a test report, the method comprising:

receiving an interpretation request sent by a client, wherein the interpretation request comprises inspection report information of a target inspection report;

determining a display mode of the test result of the target test report by using the test report information;

determining a target interpretation mode corresponding to the target inspection report according to the display mode and the interpretation mode corresponding to the display mode;

And determining an interpretation result of the target inspection report based on the inspection report information and the target interpretation mode.

In one possible implementation manner, the display manner includes numerical value display or text display, and the determining, according to the display manner and an interpretation manner corresponding to the display manner, a target interpretation manner corresponding to the target inspection report includes:

when the display mode is numerical value display, determining that a target interpretation mode of the target inspection report is conventional numerical value interpretation, wherein the conventional numerical value interpretation is to interpret the target inspection report by utilizing numerical content of numerical value display and target inspection items, and the numerical content comprises inspection result values and/or judgment symbols;

and when the display mode is text display, determining that the target interpretation mode of the target inspection report is semantic analysis interpretation, wherein the semantic analysis interpretation is to interpret the target inspection report by using a preset medical semantic analysis model and text content of the text display.

In one possible implementation, the determining the interpretation result of the target inspection report based on the inspection report information and the target interpretation mode includes:

When the target interpretation mode is conventional numerical interpretation, extracting numerical content and medical terms in the inspection report information;

determining a target test item of the medical term, searching the target test item in a preset medical knowledge base, and determining candidate knowledge with a corresponding relation with the target test item, wherein the medical knowledge base comprises a pre-recorded corresponding relation between the test item and knowledge, and the knowledge refers to medical interpretation content of the test item corresponding to the medical knowledge base;

and determining target knowledge of the target inspection item according to the numerical content and the candidate knowledge.

In one possible implementation manner, the determining the interpretation result of the target inspection report based on the inspection report information and the target interpretation manner further includes:

when the target interpretation mode is semantic analysis interpretation, extracting text content displayed in the inspection report information;

inputting the text content into the medical semantic analysis model, outputting target medical terms corresponding to the text content, wherein the medical semantic analysis model is trained based on a preset medical term database, and is used for analyzing the matching degree between a first medical term included in the text content and a second medical term in the medical term database, and outputting candidate medical terms meeting medical term selection conditions as target medical terms;

Determining a target inspection item and a target detection result of the target medical term, searching the target inspection item in a preset medical knowledge base, and determining candidate knowledge with a corresponding relation with the target inspection item, wherein the medical knowledge base comprises a pre-recorded corresponding relation between the inspection item and knowledge, and the knowledge refers to medical interpretation content of the inspection item corresponding to the medical knowledge base;

and determining target knowledge of the target inspection item according to the target detection result and the candidate knowledge.

In one possible implementation, the knowledge includes questions and answers, and the method further includes:

if any answer of the target knowledge comprises a document retrieval identification, carrying out document matching by using the test result value, a target retrieval problem and a medical semantic matching model to obtain a target reference document, wherein the target retrieval problem is a problem included in the target knowledge comprising the document retrieval identification in the answer, and the medical semantic matching model is obtained by training a preset medical document library;

and associating the target reference with the target retrieval problem to determine target knowledge of the target inspection item.

In one possible implementation, the performing document matching using the test result value, the target retrieval problem, and the medical semantic matching model to obtain a target reference includes:

inputting the target retrieval problem into a medical semantic matching model to obtain a first candidate document corresponding to the target retrieval problem and the matching degree of the target retrieval problem and the first candidate document;

inputting the test result value into a medical semantic matching model to obtain a second candidate document corresponding to the test result value and the matching degree of the test result value and the second candidate document;

acquiring an intersection by using the first candidate document and the second candidate document to obtain a third candidate document;

and sorting the third candidate documents according to the sequence from high to low of the matching degree, and selecting the third candidate documents with the top N in the sorting result as target documents.

In one possible implementation, the method further includes:

acquiring application states of the candidate knowledge in the medical knowledge base, wherein the application states comprise available states and unavailable states;

when the application state of the candidate knowledge is an available state, determining the candidate knowledge as target knowledge;

And when the application state of the candidate knowledge is an unavailable state, determining that the candidate knowledge is not target knowledge.

To achieve the above object, a second aspect of the present invention provides an interpretation apparatus of a test report, the apparatus comprising:

a receiving request module: the method comprises the steps of receiving an interpretation request sent by a client, wherein the interpretation request comprises inspection report information of a target inspection report;

and a determination information module: means for determining a presentation of the inspection result of the target inspection report using the inspection report information;

the mode determining module: the target interpretation mode corresponding to the target inspection report is determined according to the display mode and the interpretation mode corresponding to the display mode;

report interpretation module: and the method is used for determining the interpretation result of the target inspection report based on the inspection report information and the target interpretation mode.

To achieve the above object, a third aspect of the present invention provides a computer-readable storage medium storing a computer program, which when executed by a processor causes the processor to perform the steps as described in the first aspect and any one of the possible implementations.

To achieve the above object, a fourth aspect of the present invention provides a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps as described in the first aspect and any one of the possible implementations.

The embodiment of the invention has the following beneficial effects:

the invention provides an interpretation method of a test report, which comprises the following steps: receiving an interpretation request sent by a client, wherein the interpretation request comprises inspection report information of a target inspection report; determining a display mode of a test result of the target test report by using the test report information; determining a target interpretation mode corresponding to the target inspection report according to the display mode and the interpretation mode corresponding to the display mode; and determining the interpretation result of the target inspection report based on the inspection report information and the target interpretation mode. When an interpretation request is received, the display mode of the inspection result of the target inspection report is obtained by utilizing the inspection report information, the target inspection report is interpreted by adopting the interpretation mode corresponding to the display mode, and the interpretation result is obtained, so that the method not only can be suitable for the interpretation of the inspection reports of different display modes, but also can realize the real-time interpretation of the target inspection report.

Drawings

In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Wherein:

FIG. 1 is a flow chart of a method for interpreting a test report in accordance with an embodiment of the present invention;

FIG. 2 is another flow chart of a method for interpreting a test report in accordance with an embodiment of the present invention;

FIG. 3 is a schematic diagram of a test report according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a medical knowledge base according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of knowledge in an embodiment of the invention;

FIG. 6 is a schematic diagram of a medical document library according to an embodiment of the present invention;

FIG. 7 is another schematic diagram of knowledge in an embodiment of the invention;

FIG. 8 is a block diagram showing a construction of an apparatus for interpreting test reports according to an embodiment of the invention;

fig. 9 is a block diagram showing the structure of a computer device according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Referring to fig. 1, fig. 1 is a flowchart of a method for interpreting a test report, which can be applied to a terminal or a server, and the method shown in fig. 1 specifically includes the following steps:

101. receiving an interpretation request sent by a client, wherein the interpretation request comprises inspection report information of a target inspection report;

it should be noted that, the interpretation method execution body of the inspection report may be a terminal or a server, where the terminal is illustrated by taking the terminal as an example, the terminal may be a computer or a mobile terminal, the terminal receives an interpretation request sent by a client, specifically, a user identifies, through the client, an interpretation two-dimensional code preset on a target inspection report, so that the client sends the interpretation request, where the interpretation request includes inspection report information of the target inspection report, and the target inspection report is an inspection report that the user uses the client to perform the interpretation of the two-dimensional code identified, where the inspection report information is structured report information of the corresponding target inspection report, including, but not limited to, inspection information corresponding to each field of the inspection report. The inspection report may be an electronic or paper inspection report, for example and without limitation, and further the inspection report information of the target inspection report is written in the decoded two-dimensional code.

It can be understood that by presetting a design of decoding two-dimension codes on the target inspection report, the decoding process of the inspection report is triggered only after the code scanning is performed manually to obtain the related medical knowledge for decoding the report, instead of triggering the decoding process when the inspection result of the report is audited, when a plurality of target inspection reports exist, the consumption of system resources can be greatly reduced, and the decoding is performed by manual real-time triggering.

102. Determining a display mode of the test result of the target test report by using the test report information;

further, each field information of the test report exists in the test report information, and the display mode of the test result can be determined by extracting the information of the test result field, wherein the display mode is the display mode of the test result, different test results can be generated due to different test scenes, different test results can be displayed in different modes, such as numerical display of blood sugar values in blood sugar tests or text display of detected nuclear types in chromosome tests, wherein the numerical display is that the test result of the test item in the test report is reflected by numerical results such as content or content change, and the like, for example, the blood sugar values of the blood sugar tests are shown above; while text is presented to reflect the test results of the test item in the test report by text results of components, etc., such as analysis of a component, such as flow cytometry, to classify bone marrow cells, the result is diagnosed as: the combination history form accords with the bone marrow image of the chronic granulocytic leukemia, and the combination flow type BCR/ABL fusion gene test comprehensive evaluation or blood anaerobic condition culture and drug sensitivity test show that the culture result shows the escherichia coli, namely certain word theories.

103. Determining a target interpretation mode corresponding to the target inspection report according to the display mode and the interpretation mode corresponding to the display mode;

it can be understood that different test reports correspond to different diagnosis conclusions, and thus, multiple different medical knowledge exists, and in this embodiment, by identifying the display mode of each report, configuring different interpretation modes through different display modes, and further configuring different interpretation modes for each type of test report according to different display modes to interpret, the interpretation of medical terms of test reports of all test items can be adapted. For example, since the diagnostic conclusion of the numerical-presentation inspection report reflects the focus depending on the data value such as the content, the interpretation mode of the type of inspection report focuses on the interpretation in combination with the numerical content, whereas the interpretation mode of the text-presentation inspection report focuses on the interpretation in combination with the text content corresponding to the component because the diagnostic conclusion of the type of inspection report reflects the focus depending on the component information of the detected substance, and thus all the reports are automatically distinguished by the distinction of the presentation mode, which reports are to be interpreted in combination with the numerical value, and which reports are to be interpreted in combination with the text.

104. And determining an interpretation result of the target inspection report based on the inspection report information and the target interpretation mode.

Further, the interpretation result of the target inspection report can be determined through the inspection report information and the target interpretation mode, for example, the meaning of the numerical change is analyzed through the numerical change trend to be used as the interpretation result, or the meaning of the text content is analyzed through the text content displayed by the text to be used as the interpretation result. The interpretation results are used for explaining medical terms of the target test report or the back meaning of the test results, so that a tested person can read and understand the test results, and the tested person can make some preliminary medical suggestions and reduce the workload.

FIG. 2 is a flowchart of a method for interpreting a test report according to an embodiment of the invention. The method shown in fig. 2 specifically comprises the following steps:

201. receiving an interpretation request sent by a client, wherein the interpretation request comprises inspection report information of a target inspection report;

202. determining a display mode of the test result of the target test report by using the test report information;

it should be noted that, the steps 201 and 202 are similar to the steps 101 and 102, and reference may be made to the foregoing descriptions of the steps 101 and 102 for avoiding repetition.

It will be appreciated that general inspection reports fall broadly into two categories: since the numerical change reflects the report of the lesion and the detected object reflects the report of the lesion, the present embodiment includes a numerical display or a text display for explanation in the display mode, and further, determining the target interpretation mode corresponding to the target inspection report according to the display mode and the interpretation mode corresponding to the display mode may include the following steps 2031 and 2032:

2031. when the display mode is numerical value display, determining that a target interpretation mode of the target inspection report is conventional numerical value interpretation, wherein the conventional numerical value interpretation is to interpret the target inspection report by utilizing numerical content of numerical value display and target inspection items, and the numerical content comprises inspection result values and/or judgment symbols;

It should be noted that, different inspection reports are used to reflect different inspection results, different inspection results reflect different meanings of the inspection results of the inspection report, the inspection report showing the results of the inspection item through the numerical display is more based on the numerical variation trend, and the decisive pathological information is represented by the numerical variation trend, so that the result value and the judgment symbol need to be interpreted. The detection result value is content information, for example, the ratio of a certain component in every 100mg, the judgment symbol is a comparison symbol of more than ">, less than" < ", equal to" = ", rising" +%, falling "+% or constant" - - ", and the like, and the change trend of the detection result value compared with the standard value is marked through the judgment symbol. The test result value and the judgment symbol are identified through conventional numerical interpretation, and the test report is interpreted. Referring to fig. 3, fig. 3 is a schematic diagram of an inspection report in this embodiment, where the inspection result of the inspection report is shown as a numerical value.

2032. When the display mode is text display, determining that a target interpretation mode of the target inspection report is semantic analysis interpretation, wherein the semantic analysis interpretation is to interpret the target inspection report by using a preset medical semantic analysis model and text content of text display;

Furthermore, the test report for text display shows that the conclusion of the purpose of the test form is focused on the text content, and the decisive pathological information is represented by means of the text conclusion of the text content, so that the text content is utilized for interpretation. The medical semantic analysis model is a medical semantic analysis model obtained by carrying out model training in advance by utilizing medical knowledge, and the trained medical semantic analysis model has learning and reasoning capabilities and can identify medical related professional names such as 'diseases', 'microorganisms' and the like, namely various medical terms, from report results; further, it may also be possible to infer that, on the basis of the identified professional name and the pre-learning, the exemplary "escherichia coli" belongs to the genus "escherichia", and once the report appears, the bacteria "escherichia coli" belongs to the genus "escherichia" can be identified by using the medical semantic analysis model, and if the report refers to CML, the system can know that the CML is "chronic granulocytic leukemia", so that each medical term is accurately obtained in a section of diagnosis conclusion made of text.

It should be noted that, by configuring different interpretation modes for different presentation modes, all reports are automatically distinguished, which needs to walk the artificial intelligent channel to perform semantic analysis by using the medical semantic analysis model to perform interpretation, and which does not need to walk the artificial intelligent channel to perform semantic analysis by using the medical semantic analysis model to perform interpretation, so that different types of inspection reports can be interpreted pertinently, and the interpretation efficiency can be improved.

204. And determining an interpretation result of the target inspection report based on the inspection report information and the target interpretation mode.

It should be noted that, the content of step 204 is similar to that of step 104, and for avoiding repetition, reference is made to the above-mentioned content of step 104 for details.

The method comprises the steps 2031 and 2032 of judging the display modes of the inspection reports, and further adopting different interpretation modes, so that the system energy consumption can be saved, the system can know in advance which inspection reports need to go through a numerical value type path, namely conventional numerical value interpretation, which reports need to enter a semantic analysis path, namely semantic analysis interpretation, and which reports need to enter a document retrieval path, namely document retrieval interpretation.

In this possible implementation, step 204 specifically includes:

204a, extracting the numerical content and the medical term in the inspection report information when the target interpretation mode is conventional numerical interpretation;

it should be noted that, each inspection report has a corresponding medical term and a numerical content, the numerical content includes an inspection result value and/or a judgment symbol, when the display mode of the inspection result is a numerical display mode, the target interpretation mode of the inspection report is a conventional numerical interpretation mode, so that the numerical content and the medical term in the inspection report information can be extracted, and the required numerical content and medical term can be obtained by extracting the corresponding field information. Taking fig. 3 as an example, the medical terms may be "glycosylated hemoglobin component", "glycosylated hemoglobin" and "total glycosylated hemoglobin" corresponding to the item field, and "high performance liquid chromatography" corresponding to the test method field, and the digital content may be "4.9", "6.1" corresponding to the result field, and numerical related information such as the unit field, the reference interval field, and so on.

204b, determining a target test item of the medical term, searching the target test item in a preset medical knowledge base, and determining candidate knowledge with a corresponding relation with the target test item, wherein the medical knowledge base comprises a corresponding relation between a pre-recorded test item and knowledge, and the knowledge refers to medical interpretation content of the test item corresponding to the medical knowledge base;

Further, the target test item can be determined through the extracted medical terms, the target test item is searched in a preset medical knowledge base, candidate knowledge related to the target test item is located, it can be understood that different test results exist in the same test item, different test results can be read, a plurality of related knowledge can exist for reading, a plurality of knowledge can exist for each test result and are related to each test result, and then the knowledge related to the target test item is used as a candidate item for reading the target test report. Referring to fig. 4, fig. 4 is a schematic diagram of a medical knowledge base in an embodiment of the present invention, where the medical knowledge base is a medical knowledge base in which a plurality of pieces of knowledge are pre-recorded, each piece of knowledge includes a test item, a test result value, a question, an answer, and an application state, and as shown in fig. 4, an "ID" field indicates a number of each piece of knowledge, an "item name" field indicates a test item, an "associated Q & a title" field records a question and an answer corresponding to the question, an "result expression trend" field indicates a result test value and/or a judgment symbol, and an "on state" indicates an application state. Wherein, any value in the result expression trend represents that when the value of the test result is a numerical value, any value range of the numerical value is suitable for the solution of the same knowledge; "increase" means that the increase in the value corresponds to a knowledge solution; "decrease" represents a decrease in the value corresponding to a solution of knowledge, each knowledge. The laboratory will be configured according to the nature of the knowledge, i.e. the questions the knowledge includes, the resulting trend of performance corresponding to the questions, and the answers to the questions. Various kinds of knowledge can exist in each test result due to different problems, such as blood drawing projects of blood sugar detection, the display mode of the result is numerical display, and three kinds of corresponding knowledge can exist:

1 st, if the trend of the blood glucose test results is whether the test value is increased, decreased or normal, then the trend of the knowledge results will be set to any value, for example, the question of the knowledge is "interval of blood glucose concentration", then the trend of the knowledge results will be "any value", and the answer corresponding to the question will be "normal person has fasting blood glucose concentration of 3.61-6.11 mmol/L; fasting blood glucose concentrations exceeding 7.0mmol/L are referred to as hyperglycemia; blood glucose concentrations below 3.61mmol/L are referred to as hypoglycemia.

2 nd, if the blood glucose test result shows that the test value is increased, the result shows that the test value is increased, for example, the problem of the knowledge is that the blood glucose increase is visible in the disease, and the result shows that the test value is increased, and the answer to the corresponding problem is that the blood glucose increase is visible in the disease, please refer to the following: lactic acidosis, hypertension, diabetes, nephropathy, coma, diabetic neuropathy, diabetic lactic acidosis, diabetic ketoacidosis, diabetic foot, gestational diabetes complicated with diabetes, type I diabetes, type II diabetes, diabetic nephropathy, etc.

3 rd, if the blood glucose test result shows that the test value is reduced, the result shows that the test value is reduced, for example, the problem of the knowledge is that the blood glucose is reduced and the disease is visible, and the result shows that the test value is reduced, and the answer of the corresponding problem is that the blood glucose is reduced and the disease is visible, please refer to the following: the hypoglycemia syndrome (hypoglycemic syndrome) is a group of syndromes caused by various etiologies. Blood glucose concentrations often below 3.36mmol/L (60 mg/dl), and severe and prolonged hypoglycemia can occur with extensive neurological damage and complications. Common are functional hypoglycemia and hepatic hypoglycemia, etc.

It should be noted that the foregoing is merely an example, and not limiting the application, and each piece of knowledge in the present embodiment may configure the result presentation trend corresponding to the problem according to the interpretation property of the knowledge, that is, what kind of problem to be interpreted, and may be freely configured by laboratory staff.

204c, determining target knowledge of the target inspection item according to the numerical content and the candidate knowledge.

Further, using the numerical content, a target knowledge of the target verification item that matches the numerical content can be selected from the candidate knowledge. By way of example, it can be seen that ID9 in FIG. 4 means: when Human Chorionic Gonadotrophin (HCG), serum, quantitative, and digital content, i.e., test result, is increased, the target knowledge of the test report can be obtained in a preset knowledge base as interference of blood to blood HCG specimen.

It should be noted that 204a, 204b, and 204c are the interpretation modes of the digitally displayed test report in this embodiment, by inputting the related knowledge of each item related to the value change trend into the knowledge base, when the corresponding item and the value change trend appear in the test report are identified, the interpretation result of the test item or the test report can be obtained by searching in the knowledge base, the interpretation result is represented by the question and the answer of each knowledge, and further the target knowledge can be taken as the interpretation result of the report or the item, and returned to the client for presentation, and in combination with fig. 2, the blood glucose detection result can be known as the presentation form of the value, wherein, since the detected value of the blood glucose is represented by the concentration value, if the value is a value, there is a judgment of increasing and decreasing, when the value content of the corresponding test result is utilized to determine that the corresponding result representation trend of the blood glucose detection item is any value, or at least one corresponding target knowledge is represented when the corresponding trend is at least one of the "increasing" or "decreasing", and exemplary reference can be made to fig. 5, fig. 5 is a schematic diagram 5, the graph 5 is a graph of one of the items detected by the current of the knowledge, and the graph 5 is represented by the interpretation result, and the graph is represented by the graph, wherein the graph 5 is represented by the graph, the graph is shown as the graph, and the graph of the graph, and the graph is shown as the figure, and the graph. It can be understood that the interpretation contents corresponding to different knowledge are different, and the interpretation contents combine with the influence of the numerical expression trend on the test result of the test item, so as to give different interpretation, for example, the interpretation of a warm suggestion for controlling blood sugar in a blood sugar test scene and related nouns, and further, the interpretation contents of the knowledge are set and updated by laboratory staff.

In one possible implementation, if the text is presented, the step 204 of obtaining the interpretation result of the inspection report may further include steps 204i, 204ii, 204iii, 204iv:

204i, extracting text content displayed in the inspection report information when the target interpretation mode is semantic analysis interpretation;

it should be noted that, if the test result is a text presentation, text content in the test report information is extracted, specifically, conclusion content of the test result field may be extracted, for example, the test result: the text content of the text detection conclusion, such as 'combining the medical history form with the chronic myeloid leukemia bone marrow image, please combine the comprehensive evaluation of the flow type BCR/ABL fusion gene detection', or 'the blood anaerobic condition culture + the drug sensitivity test culture result to appear the escherichia coli'.

204ii, inputting the text content into the medical semantic analysis model, outputting target medical terms corresponding to the text content, wherein the medical semantic analysis model is trained based on a preset medical term database, and is used for analyzing the matching degree between a first medical term included in the text content and a second medical term in the medical term database, and outputting candidate medical terms meeting medical term selection conditions as target medical terms;

Further, the text content is input into a medical semantic analysis model, and target medical terms corresponding to the text content are output, wherein the medical semantic analysis model is trained based on a preset medical term database, the medical term database comprises proper subject terms of various subjects related to medicine, such as 'medical terms of microbiology' and 'medical terms of genetics', and the like, and a term set of medical related subjects, wherein the medical terms of microbiology comprise hierarchical relationships of phylum schematic genus species of each microorganism in the microbiology and names of microorganisms, and the medical terms of genetics comprise various karyotypes of chromosomes, and the like, by way of example and not limitation. Further, the medical semantic analysis model obtained through training of the medical term database is a short text matching model, after training, the medical semantic analysis model can identify text content, and further medical terms matched with the text content are obtained, specifically, through word segmentation of the text content and matching degree calculation of each word obtained and each medical term learned in advance, medical terms with matching degree meeting a threshold value in each medical term learned in advance in word segmentation results are output to serve as the medical terms of the text content, for example, the text content of ' combining medical history morphology to meet chronic granulocytic leukemia bone marrow image ' is obtained, and the corresponding medical term is ' chronic granulocytic leukemia ' through the medical semantic analysis model by combining flow type and BCR/ABL fusion gene detection comprehensive evaluation '.

204iii, determining a target examination item and a target detection result of the target medical term, searching the target examination item in a preset medical knowledge base, and determining candidate knowledge with a corresponding relation with the target examination item, wherein the medical knowledge base comprises a pre-recorded corresponding relation between the examination item and knowledge, and the knowledge refers to medical interpretation content of the examination item corresponding to the medical knowledge base;

204iv, determining target knowledge of the target inspection item according to the target detection result and the candidate knowledge.

Furthermore, the target examination item and the target detection result of the target examination report can be determined through the target medical term and a preset medical knowledge base, wherein the target examination item can be determined to be "bone marrow tissue biopsy" through the target medical term "chronic granulocytic leukemia", the result expression trend, namely, the target detection result is "chronic granulocytic leukemia", and the knowledge is further obtained as "clinical common knowledge of chronic granulocytic leukemia". Taking blood culture (anaerobic) +drug sensitivity+whole blood+qualitative detection items as an example, when the text content of the detection result is that enterobacteria are detected, the corresponding medical term of enterobacteria can be obtained through a medical semantic analysis model, and further the corresponding knowledge can be obtained by utilizing a medical knowledge base as the definition standard of enterobacteria MDR, XDR, PDR. It will be appreciated that when the presentation is a text presentation, the target test result is a medical term in the text content, such as "bone marrow tissue biopsy" for the target test item, and "chronic granulocytic leukemia" for the target test item.

Furthermore, the semantic analysis module has reasoning capability, and through learning of the hierarchical relationship, the attribute category of each bacterium can be known, and further, in the identified medical terms, for example, the identified medical term is "escherichia coli", and further, the genus related to the "escherichia coli" is identified, namely, the genus related to the "escherichia coli" is identified, and although knowledge corresponding to the "escherichia coli" does not exist in the knowledge base, the corresponding genus is "escherichia coli" is obtained through one step, and further, the corresponding knowledge interpretation condition can be obtained, namely, the result expression trend can be "escherichia coli", and further, the interpretation result of the knowledge is obtained. Since the variety of microorganisms is large, interpretation knowledge of newly detected bacteria or bacteria possibly without knowledge can be obtained based on attribute relationships of each microorganism through reasoning of the medical semantic analysis model.

It may be understood that the knowledge includes questions and answers, further, each test item may obtain multiple pieces of knowledge, when obtaining multiple pieces of knowledge, all pieces of knowledge together achieve interpretation of a test report, and it should be further noted that, an answer corresponding to a question may also need to be matched with a document to determine, for example, a test on a chromosome is generally a karyotype, a result of the detection is generally a disease common to analyze the karyotype, and the disease is commonly found in a reference document, and further the method further includes:

A. If any answer of the target knowledge comprises a document retrieval identification, carrying out document matching by using the test result value, a target retrieval problem and a medical semantic matching model to obtain a target reference document, wherein the target retrieval problem is a problem included in the target knowledge comprising the document retrieval identification in the answer, and the medical semantic matching model is obtained by training a preset medical document library;

it should be noted that, when a medical knowledge base is constructed, questions and answers are written, the answers corresponding to the questions may be a document retrieval identifier on the configuration of related knowledge of genetics, for example, the retrieval identifier is constructed through a wild card, further, the answers of the target knowledge include document retrieval identifiers, then document matching is performed by using a test result value, the target retrieval questions and a medical semantic matching model to obtain target references, the target retrieval questions are questions included in the target knowledge including the document retrieval identifiers in the answers, the medical semantic matching model is trained by using a preset medical document base, fig. 6 is a schematic diagram of a medical document base in the embodiment of the present invention, the document base is uploaded and managed manually, and when the document information of each document configuration document is uploaded, the document information includes a title, a digital object identifier (doi), a language, a test item, a magazine category and the like. Further, through the "knowledge of wild card answers" design of the medical knowledge base, the questions corresponding to the answers with the knowledge of the design are identified, and document retrieval is needed, so that a matched "target reference" is searched by using a medical semantic matching model. The knowledge is problematic, and the corresponding answer is searched by going to the literature along with the result of the report, only the question is required to be input, and the interpretation of each report is different. For example, the genetic chromosome mentioned above, the question is "which diseases the karyotype is found in", and the answer has only one identifier of the wildcard & meaning telling the interpretation system that the answer is to be found in the literature, and different answers are reported.

Further, in the step a, document matching is performed by using the test result value, the target retrieval problem and the medical semantic matching model, so as to obtain a target reference document, which includes:

a01, inputting the target retrieval problem into a medical semantic matching model to obtain a first candidate document corresponding to the target retrieval problem and the matching degree of the target retrieval problem and the first candidate document;

a02, inputting the test result value into a medical semantic matching model to obtain a second candidate document corresponding to the test result value and the matching degree of the test result value and the second candidate document;

a03, acquiring an intersection by using the first candidate document and the second candidate document to obtain a third candidate document;

and A04, sorting the third candidate documents according to the sequence of the matching degree from high to low, and selecting the third candidate document with the previous N in the sorting result as a target reference document.

For example, the first candidate document and the second candidate document can be obtained by searching the target search problem and the test result value respectively through the medical semantic matching model, the first candidate document and the second candidate document are intersected, the intersection can be obtained through the title of the document, each candidate document in the intersection is used as a third candidate document, and the first N documents are selected as target references according to the matching degree of each candidate document. The matching degree of the third candidate document can be obtained by calculating an average value of the matching degree of the first candidate document corresponding to the third candidate document and the matching degree of the second candidate document corresponding to the third candidate document, wherein the value of N is a positive integer, and the example can be 3.

B. And associating the target reference with the target retrieval problem to determine target knowledge of the target inspection item.

After obtaining the target reference, the target reference is used as an answer to the target retrieval question, and then the target reference is associated with the target retrieval question to obtain target knowledge of the target inspection item. It will be appreciated that after retrieval of the document is obtained, the target reference is passed to a medical knowledge base to obtain an interpretation of the report. An exemplary chromosome test item, when the result of the chromosome is not 46XX and 46XY, the answer to the question is changed back to contain the search identification, because when the result is not a conventional chromosome pair, a document review is required to know the relevant meaning. Therefore, through the medical semantic analysis model, a piece of knowledge can be pulled, and the appearance scene of the knowledge is as follows: the test item was chromosome analysis, and the test result values were not 46XX and 46XY. Wherein the problem of knowledge in the matching medical knowledge base is; the answer to the knowledge of which diseases the karyotype is common to is; the document retrieves wildcards. Furthermore, the medical semantic matching model is used for searching the literature, so that the literature is obtained, the literature is manually added in real time, the interpretation result can be matched with the current research level, the latest literature can be obtained through real-time literature retrieval, the research result in the latest literature can be obtained, and the interpretation result with the most indication can be obtained. Referring to fig. 7, another schematic diagram of knowledge in an embodiment of the present invention is shown, wherein the knowledge problem is "chromosome specimen in vitro preservation period", and the answer is a pre-configured answer content, and specifically, reference may be made to the content shown in fig. 7, and details are not described.

Illustratively, when the medical semantic matching model is used for searching, the target searching problem is converted into the vectorized searching problem, and the vectorized searching problem corresponding to the target searching problem and the vectorized document corresponding to the document item are obtained by converting the target searching problem and the document item in the medical document library through an encoder in the KM-BERT model. Specifically, the encoder of the penultimate layer in the KM-BERT model processes and outputs the processed data. The target retrieval problem is first converted into a vectorized retrieval problem, i.e. a vectorized representation of the target retrieval problem, by the encoder of the penultimate layer in the KM-BERT model. Further, each document is converted to obtain a vectorized document library, and the vectorized document is a vectorized representation of any document in the vectorized document library, specifically, may be a vectorized representation of a test item configured for the document. When matching the target references of the medical semantic matching model, the matching degree between the vectorized text to be matched and one vectorized document can only be calculated one by one through a second output layer in the KM-SEARCH, for example, by calculating cosine similarity, until all vectorized knowledge completes the calculation of the matching degree, and at the moment, the matching degree between all vectorized knowledge and the text to be matched is output.

In a specific embodiment, the semantic space of the vectorized literature library is used for searching vectorized literature with the front matching degree through a cosine similarity calculation and sorting method. Wherein the value range of the similarity is between-1 and 1, and the closer the result is to 1, the closer the result is to 1 in semantic space, and the closer the result is to-1, the opposite is to the result, and the specific formula is as follows:

where x is the vectorization search problem and y is a vectorization document.

By using the medical semantic matching model, a vectorized document library is established through a text library containing various document entries, so that a user can quickly find out medical knowledge associated with the text to be matched.

That is, if the answer to the knowledge has a "document retrieval" requirement, the questions of the test item and the knowledge are input into a medical semantic matching model, the medical semantic matching model learns the documents in the document library in advance, associates the documents with the questions after finding the documents, fills the answer, and pushes the answers to the client for the client to check.

In an alternative implementation, the method further includes: acquiring application states of each candidate knowledge in a medical knowledge base, wherein the application states comprise available states and unavailable states; when the application state of the candidate knowledge is an available state, determining the candidate knowledge as target knowledge; and when the application state of the candidate knowledge is an unavailable state, determining that the candidate knowledge is not the target knowledge.

It should be noted that, one piece of knowledge in the knowledge base includes a test item, a question, an answer, and a test result value, and each piece of knowledge also has an application state to determine the availability of each piece of knowledge, so that a manager can change the knowledge on the terminal in time. The application state comprises an available state or an unavailable state, each knowledge can be effectively managed and controlled through timely change or adjustment of management staff, candidate knowledge is further screened through the application state, and therefore target knowledge is obtained to read the inspection report, and accuracy of reading of the target knowledge can be effectively improved. Specifically, referring to fig. 4, the on state in fig. 4 is equivalent to the application state in the specification, where the application state of each piece of knowledge shown in fig. 4 is an unavailable state (the switch identifier is located on the left side), and if the knowledge is to be changed into the available state, the switch identifier can be switched to be located on the right side by clicking the switch identifier.

Further, through the above process, the target knowledge corresponding to the target inspection report can be determined to read the target inspection item, where if the report has the corresponding read information after analysis, i.e. the target knowledge, the user can be prompted at the client, for example, a button for "reporting to read and click on" is set, and if no read information exists, the button is not displayed. To prompt the user.

The invention provides an interpretation method of a test report, which comprises the following steps: receiving an interpretation request sent by a client, wherein the interpretation request comprises inspection report information of a target inspection report; determining a display mode of a test result of the target test report by using the test report information; when the display mode is numerical display, determining that the target interpretation mode of the target inspection report is conventional numerical interpretation, wherein the conventional numerical interpretation is to interpret the target inspection report by utilizing numerical content of the numerical display and target inspection items, and the numerical content comprises inspection result values and/or judgment symbols; when the display mode is text display, determining that the target interpretation mode of the target inspection report is semantic analysis interpretation, wherein the semantic analysis interpretation is to interpret the target inspection report by using a preset medical semantic analysis model and text content of the text display; and determining the interpretation result of the target inspection report based on the inspection report information and the target interpretation mode. When an interpretation request is received, the interpretation mode of the target inspection report is obtained by using the inspection report information, the target inspection report is interpreted by adopting the interpretation mode corresponding to the display mode, the interpretation result is obtained, the method not only can adapt to the interpretation of the inspection reports of different display modes, but also can realize the real-time interpretation of the target inspection report, the text content displayed by the text is subjected to semantic analysis by combining with a medical semantic analysis model, the interpretation result of the inspection report is obtained, the interpretation method is applicable to the interpretation of the digital content and the text content, and when target knowledge in a medical knowledge base comprises a document retrieval identifier, the document retrieval can be performed by using a medical semantic matching model, so that the method can also be used for the interpretation of the inspection report of complex items, and the interpretation result has real-time property.

Referring to fig. 8, fig. 8 is a schematic diagram illustrating an apparatus for interpreting a test report according to an embodiment of the invention, the apparatus includes:

the receive request module 801: the method comprises the steps of receiving an interpretation request sent by a client, wherein the interpretation request comprises inspection report information of a target inspection report;

the determination information module 802: means for determining a presentation of the inspection result of the target inspection report using the inspection report information;

mode determination module 803: the target interpretation mode corresponding to the target inspection report is determined according to the display mode and the interpretation mode corresponding to the display mode;

report interpretation module 804: and the method is used for determining the interpretation result of the target inspection report based on the inspection report information and the target interpretation mode.

It should be noted that, the functions of the modules shown in fig. 8 are similar to those of the steps shown in fig. 1, and reference may be made to the details of the steps shown in fig. 1 to avoid repetition of the description.

The invention provides an interpretation device of a test report, comprising: a receiving request module: the method comprises the steps of receiving an interpretation request sent by a client, wherein the interpretation request comprises inspection report information of a target inspection report; and a determination information module: a presentation means for determining a test result of the target test report using the test report information; the mode determining module: the method comprises the steps of determining a target interpretation mode corresponding to a target inspection report according to a display mode and an interpretation mode corresponding to the display mode; report interpretation module: and the method is used for determining the interpretation result of the target inspection report based on the inspection report information and the target interpretation mode. When an interpretation request is received, the display mode of the inspection result of the target inspection report is obtained by utilizing the inspection report information, the target inspection report is interpreted by adopting the interpretation mode corresponding to the display mode, and the interpretation result is obtained, so that the method not only can be suitable for the interpretation of the inspection reports of different display modes, but also can realize the real-time interpretation of the target inspection report.

FIG. 9 illustrates an internal block diagram of a computer device in one embodiment. The computer device may specifically be a terminal or a server. As shown in fig. 9, the computer device includes a processor, a memory, and a network interface connected by a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and may also store a computer program which, when executed by a processor, causes the processor to implement the method described above. The internal memory may also have stored therein a computer program which, when executed by a processor, causes the processor to perform the method described above. It will be appreciated by those skilled in the art that the structure shown in fig. 9 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, a computer device is presented comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method as shown in fig. 1 or fig. 2.

In an embodiment, a computer-readable storage medium is proposed, storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method as shown in fig. 1 or fig. 2.

Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims

1. A method of interpretation of a test report, the method comprising:

Determining an interpretation result of the target inspection report based on the inspection report information and the target interpretation mode;

the display mode includes numerical value display or text display, and the determining, according to the display mode and an interpretation mode corresponding to the display mode, a target interpretation mode corresponding to the target inspection report includes:

2. The method of claim 1, wherein the determining the interpretation of the target inspection report based on the inspection report information and the target interpretation comprises:

3. The method of claim 1, wherein the determining the interpretation of the target inspection report based on the inspection report information and the target interpretation, further comprises:

4. A method according to claim 2 or 3, wherein the knowledge comprises questions and answers, the method further comprising:

5. The method of claim 4, wherein the performing document matching using the test result value, the target retrieval problem, and the medical semantic matching model to obtain the target reference comprises:

6. The method according to claim 5, further comprising:

7. An apparatus for interpreting a test report, the apparatus comprising:

report interpretation module: the method comprises the steps of determining an interpretation result of a target inspection report based on the inspection report information and the target interpretation mode;

the mode determining module is specifically configured to: when the display mode is numerical value display, determining that a target interpretation mode of the target inspection report is conventional numerical value interpretation, wherein the conventional numerical value interpretation is to interpret the target inspection report by utilizing numerical content of numerical value display and target inspection items, and the numerical content comprises inspection result values and/or judgment symbols; and when the display mode is text display, determining that the target interpretation mode of the target inspection report is semantic analysis interpretation, wherein the semantic analysis interpretation is to interpret the target inspection report by using a preset medical semantic analysis model and text content of the text display.

8. A computer readable storage medium storing a computer program, which when executed by a processor causes the processor to perform the steps of the method according to any one of claims 1 to 6.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program which, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 6.